Jetson Xavier NX/Introduction/Overview: Difference between revisions

From RidgeRun Developer Wiki
(Created page with "<noinclude> {{JetsonXavierNX/Head|previous=Introduction|next=Introduction/Getting_Started|title=NVIDIA Jetson Xavier NX SoM Overview|description=This page provides a general o...")
 
 
(20 intermediate revisions by 2 users not shown)
Line 1: Line 1:
<noinclude>
<noinclude>
{{JetsonXavierNX/Head|previous=Introduction|next=Introduction/Getting_Started|title=NVIDIA Jetson Xavier NX SoM Overview|description=This page provides a general overview of the Jetson Xavier NX SoM|keywords=SoM,System on Module,hardware,peripherals,processor,processor specification,peripherals,package,developer kit,developer tools,specification}}
{{JetsonXavierNX/Head|previous=Introduction|next=Introduction/Developer_Kit|title=NVIDIA Jetson Xavier NX SoM Overview|metadescription=This page provides a general overview of the Jetson Xavier NX SoM|metakeywords=SoM, System on Module, hardware, peripherals, processor, processor specification, peripherals, package, Jetson Xavier NX developer kit, Jetson Xavier NX developer tools, specification, Jetson AGX Xavier Developer Kit, Volta GPU, Jetson Xavier NX Block Diagram}}
</noinclude>
</noinclude>


<!-- If you want a custom title for the page, un-comment and edit this line:
<!-- If you want a custom title for the page, un-comment and edit this line:
{{DISPLAYTITLE:Jetson Nano - <descriptive page name>|noerror}}
{{DISPLAYTITLE:Jetson Xavier NX - <descriptive page name>|noerror}}
-->
-->


==Hardware Overview==
==Hardware Overview==


NVIDIA designed this platform emphasizing in the following three key features:
NVIDIA designed this platform emphasizing the following three key features:


'''Small size'''
* '''Small size'''
The NVIDIA Jetson Xavier NX has a '''''70 mm x 45 mm SoC''''' where the power of an NVIDIA Xavier SoC is packed into a module the size of a Jetson Nano. This small module combines exceptional performance and power advantages with a rich set of IOs—from high-speed CSI and PCIe to low-speed I2Cs and GPIOs. We are now able to take advantage of the small form factor, sensor-rich interfaces, and big performance to bring new capability to all our embedded AI and edge systems.


'''Huge Performance'''
The NVIDIA Jetson Xavier NX has a '''''70 mm x 45 mm SoC''''' where the power of an NVIDIA Xavier SoC is packed into a module the size of a Jetson Nano. This small module combines exceptional performance and power advantages with a rich set of IOs—from high-speed CSI and PCIe to low-speed I2Cs and GPIOs. We are now able to take advantage of the small form factor, sensor-rich interfaces, and big performance to bring a new capability to all our embedded AI and edge systems.
This platform delivers up to 21 TOPS at 15 W, making it ideal for high-performance compute and AI in embedded and edge systems with size and power-constrained requirements. With 384-CUDA/48-Tensor cores Volta GPU, 2 NVIDIA Deep Learning Accelerators (NVDLA) engines, 6 Carmel ARM CPUs, video encode/decode hardware accelerators, plus 51GB/s of memory bandwidth, makes it the ideal platform to run multiple modern neural networks in parallel and process high-resolution data from multiple sensors simultaneously.


'''Power efficiency'''
* '''Huge Performance'''
The NVIDIA Jetson Xavier NX supports multiple power modes with high performance capabilities that delivers up to 21 TOPS at 15 W and 14 TOPS at 10 W. This makes this platform ideal for battery-operated systems that demands high processing resources and that share the power budgets with sensors and peripherals. This platform enables the entire NVIDIA software stack that runs all modern AI networks and frameworks with accelerated libraries for deep learning as well as computer vision, computer graphics, multimedia, and more. And it still leaves more of the available power budget for the sensors and peripherals required by today's popular embedded applications.
 
This platform delivers up to 21 TOPS at 15 W, making it ideal for high-performance computing and AI in embedded and edge systems with size and power-constrained requirements. With 384-CUDA/48-Tensor cores Volta GPU, 2 NVIDIA Deep Learning Accelerators (NVDLA) engines, 6 Carmel ARM CPUs, video encode/decode hardware accelerators, plus 51GB/s of memory bandwidth, make it the ideal platform to run multiple modern neural networks in parallel and process high-resolution data from multiple sensors simultaneously.
 
* '''Power efficiency'''
 
The NVIDIA Jetson Xavier NX supports multiple power modes with high performance capabilities that deliver up to 21 TOPS at 15 W and 14 TOPS at 10 W. This makes this platform ideal for battery-operated systems that demand high processing resources and that share the power budgets with sensors and peripherals. This platform enables the entire NVIDIA software stack that runs all modern AI networks and frameworks with accelerated libraries for deep learning as well as computer vision, computer graphics, multimedia, and more. And it still leaves more of the available power budget for the sensors and peripherals required by today's popular embedded applications.




=== Processing Specifications ===
=== Processing Specifications ===
{| class="wikitable" style="color:black; background-color:#f6f6f6; margin: auto;"
{| class="wikitable" style="text-align: center; margin-left: auto; margin-right: auto; border: none;
|+Table 1. Processing Specifications
|-
!  !! '''10 W''' !! '''15 W'''
|-
| '''AI Performance''' || 14 TOPS (INT8) || 21 TOPS (INT8)
|-
| '''GPU''' || colspan="2" | 384-core NVIDIA Volta™ GPU with 48 Tensor Cores
|-
| '''GPU Max Freq''' || 800 MHz || 1100 MHz
|-
| '''CPU''' || colspan="2" | 6-core NVIDIA Carmel ARM®v8.2 64-bit CPU<br>6MB L2 + 4MB L3
|-
| '''CPU Max Freq''' || 2-core @ 1500MHz<br>4-core @ 1200MHz || 2-core @ 1900MHz<br>4/6-core @ 1400Mhz
|-
| '''Memory''' || colspan="2" | 8 GB 128-bit LPDDR4x @ 1600 MHz<br>51.2GB/s
|-
| '''Storage''' || colspan="2" | 16 GB eMMC 5.1
|-
| '''Power''' || colspan="2" | 10W/15W
|-
| '''PCIe''' || colspan="2" | 1 x1 + 1x4<br>(PCIe Gen3, Root Port & Endpoint)
|-
| '''CSI Camera''' || colspan="2" | Up to 6 cameras (36 via virtual channels)<br>12 lanes MIPI CSI-2<br>D-PHY 1.2 (up to 30 Gbps)
|-
| '''Video Encode''' || colspan="2" | Standards supported: H.265 (HEVC), H.264, VP9. 2x464MP/sec (HEVC)<br>2x 4K @ 30 (HEVC)<br>6x 1080p @ 60 (HEVC)<br>14x 1080p @ 30 (HEVC)
|-
| '''Video Decode''' || colspan="2" | Standards supported: H.265 (HEVC), H.264, VP9, VP8, MPEG-4, MPEG-2, VC-1. 2x690MP/sec (HEVC)<br>2x 4K @ 60 (HEVC)<br>4x 4K @ 30 (HEVC)<br>12x 1080p @ 60 (HEVC)<br>32x 1080p @ 30 (HEVC)<br>16x 1080p @ 30 (H.264)
|-
| '''Display''' || colspan="2" | 2 multi-mode DP 1.4/eDP 1.4/HDMI 2.0
|-
| '''DL Accelerator''' || colspan="2" | 2x NVDLA Engines
|-
| '''Vision Accelerator''' || colspan="2" | 7-Way VLIW Vision Processor
|-
| '''Networking''' || colspan="2" | 10/100/1000 BASE-T Ethernet
|-
| '''Mechanical''' || colspan="2" | 45 mm x 69.6 mm<br>260-pin SO-DIMM connector
|}
 
=== Interfaces ===
 
{| class="wikitable" style="margin-left: auto; margin-right: auto; border: none;
|-
!  Category !! '''Function''' !! style="border-left:solid 5px black;" | Category !! '''Function'''
|-
| '''USB''' || USB 2.0 interface (3x)<br>USB 3.1 (1x) || style="border-left:solid 5px black;" | '''UART''' || 3x
|-
| '''PCIe''' || PCIe (x1 and x4) || style="border-left:solid 5px black;" |  '''SPI''' || 2x
|-
| '''Camera''' || CSI (3 x4 or 6 x2)<br>Control, clock || style="border-left:solid 5px black;" | '''CAN''' || 1x
|-
|-
! Feature
| '''Display''' || HDMI/eDP/DP (2x)<br>DP_AUX/HPD (2x), CEC (1x)  || style="border-left:solid 5px black;" | '''Wi-Fi/BT/Modem''' || PCIe/UART/I2S, control/handshake
! Description
|-
|-
| '''GPU'''
| '''Audio''' || I2S interface (2x) and clock<br>Master clock || style="border-left:solid 5px black;" | '''Fan''' || FAN PWM and tach input
| 128 Core Maxwell 0.5 TFLOPs (FP16)
|-
|-
| '''CPU'''
| '''SD Card/SDIO''' || SD Card or SDIO interface (1x) || style="border-left:solid 5px black;" | '''Debug''' || UART
| 4 core ARM A57 @ 1.43 GHz
|-  
| '''Memory'''
| 4 GB 64 bit LPDDR4 25.6 GB/s
|-
|-
| '''Storage'''
| '''LAN''' || Gigabit ethernet || style="border-left:solid 5px black;" | '''System''' || Power control, reset, alerts
| 16 GB eMMC
|-
|-
| '''Encoder'''
| '''I2C''' || 4x || style="border-left:solid 5px black;" | '''Power''' || Main input and battery back-up for RTC
| H.264/H.265 up to  4K@30, 4 x 1080p@30, 9 x 720p@30
|-
|-
| '''Decoder'''
| H.264/H.265 up to  4K@60, 2 x 4K@20, 8 x 1080p@30, 18 x 720p@30
|-
|}
|}


=== Peripherals ===
===Jetson Xavier NX Block Diagram===


* 1 x1/2/4 PCIE
The hardware described in the key features and interfaces table can be observed in the following block diagram:
* 1 USB 3.0
<br>
* SD/MMC Controller
<br>
* Display
[[Image:BlockXavierNX.png|thumb|center|600px]]
** HDMI 2.0 or DP1.2
<div style="text-align: center;">NVIDIA Jetson Xavier NX block diagram.</div>
** Up to 2 simultaneous displays
* Camera
** 12 (3x4 or 4x2) MIPI CSI-2 DPHY 1.1 lanes (1.5 Gbps)
** Compatible with Raspberry-Pi v2 camera module
* WiFi/BT — equires external chip
* 1 x SDIO
* 2 x SPI
* 5 x SysIO
* 3 x GPIOs
* 6 x I2C


=== Package ===
=== Package ===
{| class="wikitable" style="color:black; background-color:#f6f6f6; margin: auto;"
{| class="wikitable" style="color:black; background-color:#f6f6f6; margin: auto;"
|+Table 2. Package
|-
|-
! Feature  
! Feature  
Line 80: Line 109:
|-
|-
| '''Operating Temperature'''
| '''Operating Temperature'''
| Range from -25 – 80C
| Range from -20 – 80 °C
|-
|-
| '''Power Input'''
| '''Power Input'''
| 5.0V
| 9 – 19 V / 5 A max (DevKit), 5 V (Module)
|-
|-
| '''Module Power'''
| '''Module Power'''
| 5 – 25W
| 10 – 15 W
|-
|-
|}
|}


===Developer Kit===
===Jetson Xavier NX Developer Kit===
The developer kit comes with a MIPI-CSI camera connector to enable video applications, as well as an ethernet port, HDMI output, and four USB ports. A 5V/4A source is required to power the kit. Other features offered in the development kit are:
The developer kit comes with 2x MIPI-CSI 15 pin camera connectors to enable video applications, as well as a Gigabit Ethernet port, WiFi, Bluetooth, HDMI output, Display Port output, 4x USB ports, USB 2.0 Micro-B port, and 40-pin header port. A 19V/3.4A power supply is included to power the Xavier NX developer kit. A micro SD card (not included) is required to flash the system image and boot the board. Other features offered in the development kit accessible through the 40-pin header port are:


* GPIO
* GPIO
Line 98: Line 127:
* SPI
* SPI
* UART
* UART
* Display port
* PCIe


The Jetson Nano developer kit requires an external chip for WiFi and/or Bluetooth and unlike other devkits in the Jetson family, it does not support USB OTG.
==Jetson Xavier NX Developer Tools==


==Developer Tools==
Software development can be done using NVIDIA's Jetpack, as in other NVIDIA Jetson boards. The image generated by Jetpack can be flashed into an SDCard to boot Jetson Xavier NX. Jetpack provides Ubuntu 18.04 OS with kernel 4.9. Please follow [https://developer.nvidia.com/embedded/jetpack  JetPack installation steps]. For AI and parallel computing applications, Jetpack provides CUDA, cuDNN, DeepStream, and TensorRT. Additionally, tools like nvpmodel to control the power/performance profile and tegrastats that provide CPUs and GPU stats, come with the filesystem.


Software development can be done using NVIDIA's Jetpack, as in other NVIDIA Jetson boards. The image generated by Jetpack can be flashed into an SDCard to boot Jetson Nano. Jetpack provides Ubuntu 18.04 OS with kernel 4.9, find the information about how to install JetPack in [[#Related_Documentation|Related Documentation]]. For AI and parallel computing applications, Jetpack provides CUDA, cuDNN, and TensorRT. Additionally, tools like nvpmodel to control the power/performance profile and tegrastats that provide CPUs and GPU stats, come with the filesystem.
The 384-core Volta GPU supports OpenGL 4.6, OpenGL ES 3.2, and Vulkan 1.2 as well.


The 128-core Maxwell GPU supports OpenGL 4.6, OpenGL ES 3.2 and Vulkan 1.1 as well.
==Jetson Family Comparison==
 
{| class="wikitable" style="text-align: center; margin-left: auto; margin-right: auto; border: none;
==Jetson Nano vs Jetson TX1==
|-
Nano and TX1 are not pin compatible, however, they share common features, like USB 3.0 and CSI. Both come with the same size of eMMC and memory. Encode/decode capabilities also remain the same. While TX1 has 256-core GPU, Nano comes with 128-core, both NVIDIA Maxwell GPUs. Nano CPU has a lower frequency of 1.43 GHz compared with TX1 CPU frequency of 1.7 GHz. The differentiator of the Jetson Nano with respect to other boards in the Jetson family is its low power consumption, it requires an input voltage of 5 V while TX1 input voltage vary between 5.5 V and 19.6 V.
!  !! '''Jetson Nano''' !! '''Xavier NX (10 W)''' !! '''Xavier NX (15 W)''' !! '''AGX Xavier'''
|-
| '''CPU''' || 4x Cortex-A57 @ 1.43GHz || 4x/ Carmel @ 1.2GHz<br>or<br>2x Carmel @ 1.5GHz || 4x/6x Carmel @ 1.4GHz<br>or<br>2x Carmel @ 1.9GHz || 8x Carmel @ 2.26GHz
|-
| '''GPU''' || Maxwell, 128 Cores @ 920MHz || Volta, 384 Cores @ 800MHz || Volta, 384 Cores @ 1100MHz || Volta, 512 Cores @ 1377MHz
|-
| '''Accelerators''' || N/A || colspan="2" | 2x NVDLA || 2x NVDLA
|-
| '''Memory''' || 4GB LPDDR4,<br>64-bit bus<br>(25.6 GB/sec) || colspan="2" | 8GB LPDDR4X,<br>128-bit bus<br>(51.2 GB/sec) || 16GB LPDDR4X,<br>256-bit bus<br>(137 GB/sec)
|-
| '''Storage''' || 16GB eMMC || colspan="2" | 8GB eMMC  || 32GB eMMC
|-
| '''AI Performance''' || N/A || 14 TOPS || 21 TOPS || 32 TOPS
|-
| '''Dimensions''' || 45mm x 70mm || colspan="2" | 45mm x 70mm || 100mm x 87mm
|-
| '''TDP''' || 10W || 10W || 15W || 30W
|-
| '''Module Price''' || $149 ||  colspan="2" | $499 || $999
|-
| '''DevKit Price''' || $99 ||  colspan="2" | $399 || $699
|-
|}


====Compatibility with Jetson AGX Xavier====


An alternative to starting developing for Jetson Xavier NX is using the Jetson AGX Xavier Developer Kit. You just need to {{Download}} download [https://developer.nvidia.com/embedded/downloads#?search=Jetson%20AGX%20Xavier%20as%20Jetson%20Xavier%20NX%20Emulation%20Package the software patch] and install it on your Jetson Xavier AGX Developer Kit.


<noinclude>
<noinclude>
{{JetsonNano/Foot|Introduction|Introduction/Getting_Started}}
{{JetsonXavierNX/Foot|Introduction|Introduction/Developer_Kit}}
</noinclude>
</noinclude>

Latest revision as of 18:34, 2 October 2023



Previous: Introduction Index Next: Introduction/Developer_Kit


NVIDIA®Jetson Xavier NX™
NVIDIA
Introduction
Overview
Developer Kit
Getting Started
Development
Building Kernel from Source
GStreamer
Accelerated Elements
Example Pipelines
RidgeRun Products
Contact Us




Hardware Overview

NVIDIA designed this platform emphasizing the following three key features:

  • Small size

The NVIDIA Jetson Xavier NX has a 70 mm x 45 mm SoC where the power of an NVIDIA Xavier SoC is packed into a module the size of a Jetson Nano. This small module combines exceptional performance and power advantages with a rich set of IOs—from high-speed CSI and PCIe to low-speed I2Cs and GPIOs. We are now able to take advantage of the small form factor, sensor-rich interfaces, and big performance to bring a new capability to all our embedded AI and edge systems.

  • Huge Performance

This platform delivers up to 21 TOPS at 15 W, making it ideal for high-performance computing and AI in embedded and edge systems with size and power-constrained requirements. With 384-CUDA/48-Tensor cores Volta GPU, 2 NVIDIA Deep Learning Accelerators (NVDLA) engines, 6 Carmel ARM CPUs, video encode/decode hardware accelerators, plus 51GB/s of memory bandwidth, make it the ideal platform to run multiple modern neural networks in parallel and process high-resolution data from multiple sensors simultaneously.

  • Power efficiency

The NVIDIA Jetson Xavier NX supports multiple power modes with high performance capabilities that deliver up to 21 TOPS at 15 W and 14 TOPS at 10 W. This makes this platform ideal for battery-operated systems that demand high processing resources and that share the power budgets with sensors and peripherals. This platform enables the entire NVIDIA software stack that runs all modern AI networks and frameworks with accelerated libraries for deep learning as well as computer vision, computer graphics, multimedia, and more. And it still leaves more of the available power budget for the sensors and peripherals required by today's popular embedded applications.


Processing Specifications

10 W 15 W
AI Performance 14 TOPS (INT8) 21 TOPS (INT8)
GPU 384-core NVIDIA Volta™ GPU with 48 Tensor Cores
GPU Max Freq 800 MHz 1100 MHz
CPU 6-core NVIDIA Carmel ARM®v8.2 64-bit CPU
6MB L2 + 4MB L3
CPU Max Freq 2-core @ 1500MHz
4-core @ 1200MHz		 2-core @ 1900MHz
4/6-core @ 1400Mhz
Memory 8 GB 128-bit LPDDR4x @ 1600 MHz
51.2GB/s
Storage 16 GB eMMC 5.1
Power 10W/15W
PCIe 1 x1 + 1x4
(PCIe Gen3, Root Port & Endpoint)
CSI Camera Up to 6 cameras (36 via virtual channels)
12 lanes MIPI CSI-2
D-PHY 1.2 (up to 30 Gbps)
Video Encode Standards supported: H.265 (HEVC), H.264, VP9. 2x464MP/sec (HEVC)
2x 4K @ 30 (HEVC)
6x 1080p @ 60 (HEVC)
14x 1080p @ 30 (HEVC)
Video Decode Standards supported: H.265 (HEVC), H.264, VP9, VP8, MPEG-4, MPEG-2, VC-1. 2x690MP/sec (HEVC)
2x 4K @ 60 (HEVC)
4x 4K @ 30 (HEVC)
12x 1080p @ 60 (HEVC)
32x 1080p @ 30 (HEVC)
16x 1080p @ 30 (H.264)
Display 2 multi-mode DP 1.4/eDP 1.4/HDMI 2.0
DL Accelerator 2x NVDLA Engines
Vision Accelerator 7-Way VLIW Vision Processor
Networking 10/100/1000 BASE-T Ethernet
Mechanical 45 mm x 69.6 mm
260-pin SO-DIMM connector

Interfaces

Category Function Category Function
USB USB 2.0 interface (3x)
USB 3.1 (1x)		 UART 3x
PCIe PCIe (x1 and x4) SPI 2x
Camera CSI (3 x4 or 6 x2)
Control, clock		 CAN 1x
Display HDMI/eDP/DP (2x)
DP_AUX/HPD (2x), CEC (1x)		 Wi-Fi/BT/Modem PCIe/UART/I2S, control/handshake
Audio I2S interface (2x) and clock
Master clock		 Fan FAN PWM and tach input
SD Card/SDIO SD Card or SDIO interface (1x) Debug UART
LAN Gigabit ethernet System Power control, reset, alerts
I2C 4x Power Main input and battery back-up for RTC

Jetson Xavier NX Block Diagram

The hardware described in the key features and interfaces table can be observed in the following block diagram:

NVIDIA Jetson Xavier NX block diagram.

Package

Feature Description
Module Size 69.6 mm x 45 mm
Connector 260 pin SO-DIMM
Operating Temperature Range from -20 – 80 °C
Power Input 9 – 19 V / 5 A max (DevKit), 5 V (Module)
Module Power 10 – 15 W

Jetson Xavier NX Developer Kit

The developer kit comes with 2x MIPI-CSI 15 pin camera connectors to enable video applications, as well as a Gigabit Ethernet port, WiFi, Bluetooth, HDMI output, Display Port output, 4x USB ports, USB 2.0 Micro-B port, and 40-pin header port. A 19V/3.4A power supply is included to power the Xavier NX developer kit. A micro SD card (not included) is required to flash the system image and boot the board. Other features offered in the development kit accessible through the 40-pin header port are:

  • GPIO
  • I2C
  • I2S
  • SPI
  • UART
  • PCIe

Jetson Xavier NX Developer Tools

Software development can be done using NVIDIA's Jetpack, as in other NVIDIA Jetson boards. The image generated by Jetpack can be flashed into an SDCard to boot Jetson Xavier NX. Jetpack provides Ubuntu 18.04 OS with kernel 4.9. Please follow JetPack installation steps. For AI and parallel computing applications, Jetpack provides CUDA, cuDNN, DeepStream, and TensorRT. Additionally, tools like nvpmodel to control the power/performance profile and tegrastats that provide CPUs and GPU stats, come with the filesystem.

The 384-core Volta GPU supports OpenGL 4.6, OpenGL ES 3.2, and Vulkan 1.2 as well.

Jetson Family Comparison

Jetson Nano Xavier NX (10 W) Xavier NX (15 W) AGX Xavier
CPU 4x Cortex-A57 @ 1.43GHz 4x/ Carmel @ 1.2GHz
or
2x Carmel @ 1.5GHz		 4x/6x Carmel @ 1.4GHz
or
2x Carmel @ 1.9GHz		 8x Carmel @ 2.26GHz
GPU Maxwell, 128 Cores @ 920MHz Volta, 384 Cores @ 800MHz Volta, 384 Cores @ 1100MHz Volta, 512 Cores @ 1377MHz
Accelerators N/A 2x NVDLA 2x NVDLA
Memory 4GB LPDDR4,
64-bit bus
(25.6 GB/sec)		 8GB LPDDR4X,
128-bit bus
(51.2 GB/sec)		 16GB LPDDR4X,
256-bit bus
(137 GB/sec)
Storage 16GB eMMC 8GB eMMC 32GB eMMC
AI Performance N/A 14 TOPS 21 TOPS 32 TOPS
Dimensions 45mm x 70mm 45mm x 70mm 100mm x 87mm
TDP 10W 10W 15W 30W
Module Price $149 $499 $999
DevKit Price $99 $399 $699

Compatibility with Jetson AGX Xavier

An alternative to starting developing for Jetson Xavier NX is using the Jetson AGX Xavier Developer Kit. You just need to download the software patch and install it on your Jetson Xavier AGX Developer Kit.


Previous: Introduction Index Next: Introduction/Developer_Kit



Retrieved from "https://developer.ridgerun.com/wiki/index.php?title=Jetson_Xavier_NX/Introduction/Overview&oldid=50797"